CoolFace
Modelpublic

RichardErkhov/KR-X-AI_-_krx-gemma-2-9b-nis-100-1-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes349downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

krx-gemma-2-9b-nis-100-1 - GGUF

  • —Model creator: https://huggingface.co/KR-X-AI/
  • —Original model: https://huggingface.co/KR-X-AI/krx-gemma-2-9b-nis-100-1/
NameQuant methodSize
krx-gemma-2-9b-nis-100-1.Q2_K.ggufQ2_K2.81GB
krx-gemma-2-9b-nis-100-1.IQ3_XS.ggufIQ3_XS3.12GB
krx-gemma-2-9b-nis-100-1.IQ3_S.ggufIQ3_S3.26GB
krx-gemma-2-9b-nis-100-1.Q3_K_S.ggufQ3KS3.25GB
krx-gemma-2-9b-nis-100-1.IQ3_M.ggufIQ3_M3.33GB
krx-gemma-2-9b-nis-100-1.Q3_K.ggufQ3_K3.55GB
krx-gemma-2-9b-nis-100-1.Q3_K_M.ggufQ3KM3.55GB
krx-gemma-2-9b-nis-100-1.Q3_K_L.ggufQ3KL3.81GB
krx-gemma-2-9b-nis-100-1.IQ4_XS.ggufIQ4_XS3.96GB
krx-gemma-2-9b-nis-100-1.Q4_0.ggufQ4_04.13GB
krx-gemma-2-9b-nis-100-1.IQ4_NL.ggufIQ4_NL4.16GB
krx-gemma-2-9b-nis-100-1.Q4_K_S.ggufQ4KS4.15GB
krx-gemma-2-9b-nis-100-1.Q4_K.ggufQ4_K4.36GB
krx-gemma-2-9b-nis-100-1.Q4_K_M.ggufQ4KM4.36GB
krx-gemma-2-9b-nis-100-1.Q4_1.ggufQ4_14.54GB
krx-gemma-2-9b-nis-100-1.Q5_0.ggufQ5_04.95GB
krx-gemma-2-9b-nis-100-1.Q5_K_S.ggufQ5KS4.95GB
krx-gemma-2-9b-nis-100-1.Q5_K.ggufQ5_K5.07GB
krx-gemma-2-9b-nis-100-1.Q5_K_M.ggufQ5KM5.07GB
krx-gemma-2-9b-nis-100-1.Q5_1.ggufQ5_15.36GB
krx-gemma-2-9b-nis-100-1.Q6_K.ggufQ6_K5.82GB
krx-gemma-2-9b-nis-100-1.Q8_0.ggufQ8_07.54GB

Original model description: --- base_model: KR-X-AI/krx-gemma-2-9b-nis tags:

  • —text-generation-inference
  • —transformers
  • —unsloth
  • —qwen2
  • —trl
  • —sft license: apache-2.0 language:
  • —en ---

Uploaded model

  • —Developed by: KR-X-AI
  • —License: apache-2.0
  • —Finetuned from model : KR-X-AI/krx-gemma-2-9b-nis

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>